© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150756
    Prev
    Next
    INDEX
    Explanations

    unworthiness, nervousness, yearly income

    np_acts-logits-general · gemini-2.5-flash-lite

    bolded sections or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    0.69
    া
    0.58
    ft
    0.52
    ه
    0.52
    t
    0.51
    ationale
    0.50
    ag
    0.49
    敕
    0.47
    ato
    0.47
    ftop
    0.47
    POSITIVE LOGITS
     いつ
    0.45
     नौकर
    0.44
     saddo
    0.43
     Pages
    0.43
    Pages
    0.42
     sæ
    0.42
     पलट
    0.42
    珑
    0.41
     nya
    0.41
    णारा
    0.41
    Activations Density 0.001%

    No Known Activations